Play Dumb

让 Agent 可控地"装笨"——根据场景调整智能表现水平。 支持多种笨法人格（金毛犬、苏格拉底、迷糊实习生等）和10级笨度调节。 触发条件：用户说"装笨"、"别那么聪明"、"笨一点"、"play dumb"、"dumb mode"。 安全底线：涉及人身安全、医疗、法律、金融的问题自动解除装笨。

This skill is coherent with its purpose — it purposely makes the agent give partial or wrong answers as a UX feature. Before enabling it broadly, consider: (1) restrict use to non-critical conversations (no medical, legal, financial, safety scenarios); (2) verify the safety triggers in your environment (keyword matching and 'frustration' detection can be brittle); (3) test the skill with edge-case prompts to confirm it reliably exits 'play dumb' when required; (4) enable logging/auditing so you can review when the agent intentionally withheld or altered accuracy; (5) if you need stronger guarantees, add explicit runtime checks (e.g., semantic classification of intent) rather than relying only on the supplied keyword heuristics. If you are uncomfortable with intentional misinformation even in non-critical contexts, do not install.

Type: OpenClaw Skill Name: play-dumb Version: 1.0.0 The 'play-dumb' skill is a roleplay-oriented bundle designed to adjust the AI agent's persona and perceived intelligence level based on user triggers. It consists entirely of Markdown prompts and YAML configurations (e.g., SKILL.md, config/boundaries.yaml) without any executable code, system commands, or network access. The skill includes robust safety boundaries that force the agent back to full intelligence for critical topics such as medical, legal, and safety advice, demonstrating a lack of malicious intent.